arXiv subjects

Sebastian Ziegelmayer

Publications and source records attributed to Sebastian Ziegelmayer.

12 recordsLinked to original sources

arXiv2026

RadPRISM: Schema-stratified radiology-report supervision for concept-disentangled image representations and visual grounding

Vision-language pretraining learns rich medical image representations from radiology reports, but previous model variants commonly operate within a single shared embedding space, so concept-level structure and interpretability must be recovered post hoc, limiting model transparency and, hence, clinical utility. We introduce RadPRISM, which makes a clinician-defined radiology schema a designated stratification axis: an on-premise large language model extracts per-concept text spans from free-text reports, and each clinical concept is aligned in its own dedicated visual subspace, turning concept stratification into direct, top-level alignment supervision. Instantiated on chest radiographs with a 19-concept schema over $203{,}602$ examinations from an internal multi-year archive, RadPRISM improved internal dataset zero-shot classification from $0.717$ (95% CI, $0.710-0.723$) to $0.868$ (95% CI, $0.863-0.872$) macro AUROC over a matched global-alignment baseline, performed on par with the purpose-built CARZero reference in external zero-shot classification while substantially outperforming it (up to 4.3-fold) in pointing-game visual grounding. In addition, a radiologist reader study demonstrated concept-stratified retrieval ability ($0.78$ macro retrieval correctness rate within rank 3), surfacing disentangled descriptive findings that report-level retrieval and fixed-label vocabularies cannot express. RadPRISM yields discriminative, spatially faithful, natively concept-stratified representations shaped by and transparently inspectable by clinicians.

cs.CV↗

arXiv2026

Self-supervision drives representational convergence in medical foundation models more than clinical supervision

Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scale and clinical supervision concentrate their representations onto a shared structure. Whether this convergence is real, what produces it, and whether it is clinically usable are untested, and the similarity measures behind such claims are fragile. We present a controlled dissection across 18 image and 7 text encoders, all open-weight and run locally, spanning 7M to 27B parameters and five imaging modalities, including 650,982 chest radiographs from six datasets. To isolate cause, we train encoders that vary only the objective under fixed data, architecture, and scale, and reproduce the effect in a synthetic model. Convergence is modest but above a random floor, driven by the self-supervised objective, not clinical supervision: matched self-supervised encoders aligned most (40.4% on chest radiography), with label-supervised (21.1%) and image-text (3.3%) far lower, and did not grow with size (Spearman 0.302, p=0.223) or capability. It is within-modality, does not reach clinical language, and does not reproduce how radiologists judge case similarity. Yet a linear classifier transfers across encoders and to five held-out hospitals, retaining about 85% of within-encoder performance. Convergence in medical imaging is therefore set by the pretraining objective, not inherited from scale or clinical supervision. Interoperability is accordingly something to design for through that objective, and to validate where the shared geometry is weakest, across patient subgroups and against clinical judgment.

cs.CV↗

arXiv2026

Information-seeking failures of large language models in agentic clinical reasoning

Large language models achieve high scores on medical knowledge assessments, yet clinical reasoning requires actively deciding what to investigate under uncertainty. We developed an agentic evaluation framework in hematologic oncology in which models must proactively request clinical data across three sequential rounds before committing to a diagnosis and treatment plan. Across 32 frontier models, the best achieved only 68% overall accuracy. Information utilization, the fraction of available data actually requested, was the strongest predictor of diagnostic accuracy (R = 0.69, P < 0.001), yet utilization collapsed from 57% to 26% in the final round, leaving molecular and cytogenetic data critical for treatment selection unexamined. Reasoning traces scored high on a clinical reasoning rubric (91% above threshold) but decorrelated from accuracy, revealing a gap between locally coherent rationales and globally correct conclusions. Error analysis identified search satisficing, anchoring and premature closure as the dominant failure modes, the same cognitive biases that characterize novice clinicians under dual-process models of diagnostic reasoning. These findings demonstrate that the primary limitation of current models in clinical oncology is not insufficient medical knowledge but a systematic failure of information-seeking under uncertainty.

cs.AI↗

arXiv2026

Vision-language models for chest radiography do not always need the image

Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image. That inference is unsafe: a model exploiting finding-name priors scores like one that reads the scan, and no standard benchmark separates them. We introduce a causal audit that intervenes on the image, occluding the relevant region, occluding an irrelevant one, and swapping in another patient's same-label scan, and combines three behavioral metrics to test whether a correct answer depends on the image. Across nine systems, a text-only model with no image access reaches within 5.7 accuracy points of the best multimodal one, and a 119-billion-parameter multimodal model is statistically indistinguishable from a 7-billion text-only baseline. The audit splits the cohort into three models that ignore the image, one that is unstable, and five that use it selectively, for a subset of findings; the categories hold across a second dataset, resolution, and prompt phrasing. Against board-certified radiologists, a text-only model is statistically indistinguishable from a radiologist's accuracy while grounding at zero, whereas the image-using models ground at radiologist-comparable rates. Reported confidence flags ungrounded answers only when a model uses the image. Grounding audits, not accuracy, should gate clinical deployment.

cs.CV↗

arXiv2026

Routine laboratory trajectories encode the onset of organ-level complications in cancer

Routine laboratory panels drawn during cancer treatment constitute longitudinal physiological recordings of organ function, yet their temporal structure is discarded by single-timepoint prognostic tools. A transformer trained on 2,777,595 laboratory measurements from 3,905 patients with multiple myeloma or ovarian cancer predicted the two-year onset of 162 treatment-associated complications, including therapy-related myelodysplastic syndromes, spanning eight clinical categories, achieving 1.5- to 6.1-fold enrichment above prevalence at the group level. It matched or outperformed non-sequential baselines across grouped endpoints (AUROC gains up to +0.11), demonstrating that longitudinal laboratory trajectories capture evolving complication-specific physiology inaccessible from isolated measurements. Predictions generalised across both cancers, divergence concentrating in disease-specific complications, and biomarker masking recovered signatures consistent with established pathophysiology. External validation on MIMIC-IV and MMRF CoMMpass confirmed transferability across independent healthcare systems (AUROC up to 0.85). Routine oncological laboratory data encode organ deterioration weeks to months before clinical onset, enabling complication-specific surveillance without additional testing infrastructure.

cs.LG↗

arXiv2026

Benchmarking Foundation Models for Renal Lesion Stratification in CT

The rapid proliferation of open-source medical foundation models (FMs) raises a practical question: how well do their pre-trained representations transfer to clinically relevant but data-scarce classification tasks? Particularly in CT-based renal lesion classification, a push toward greater generalizability would be meaningful, as the field is constrained by inherently limited training data. We addressed this through a benchmark of three medical FMs on this specific task. This six-class problem spans common entities like cysts and clear cell renal cell carcinoma, alongside rare subtypes. Using a frozen feature-probing protocol, we compared FM embeddings against a handcrafted radiomics classifier and a 3D ResNet-50 trained from scratch. Models were trained on a composite dataset of 2,854 lesions and evaluated on an external test set of 234 lesions from The Cancer Imaging Archive. Our results reveal two key findings. First, FM performance (AUC 0.70-0.77) matched the from-scratch ResNet (AUC 0.72) while drastically reducing hardware demand, requiring only seconds on a CPU after feature extraction. However, the conventional radiomics baseline significantly outperformed all deep learning approaches, achieving an AUC of 0.88 (all p $\leq$ 0.002). This suggests that current generalist FM embeddings do not yet capture the fine-grained texture and shape heterogeneity driving histological subtype discrimination. Despite their potential in data-scarce settings, medical FMs did not surpass established models for renal lesion stratification, leaving radiomics as the current state-of-the-art.

cs.CV↗

arXiv2026

Atomic Fact-Checking Increases Clinician Trust in Large Language Model Recommendations for Oncology Decision Support: A Randomized Controlled Trial

Question: Does atomic fact-checking, which decomposes AI treatment recommendations into individually verifiable claims linked to source guideline documents, increase clinician trust compared to traditional explainability approaches? Findings: In this randomized trial of 356 clinicians generating 7,476 trust ratings, atomic fact-checking produced a large effect on trust (Cohen's d = 0.94), increasing the proportion of clinicians expressing trust from 26.9% to 66.5%. Traditional transparency mechanisms showed a dose-response gradient of improvement over baseline (d = 0.25 to 0.50). Meaning: Decomposing AI recommendations into individually verifiable claims linked to source guidelines produces substantially higher clinician trust than traditional explainability approaches in high-stakes clinical decisions.

cs.CL↗

arXiv2026

Agentic clinical reasoning over longitudinal myeloma records: a retrospective evaluation against expert consensus

Multiple myeloma is managed through sequential lines of therapy over years to decades, with each decision depending on cumulative disease history distributed across dozens to hundreds of heterogeneous clinical documents. Whether LLM-based systems can synthesise this evidence at a level approaching expert agreement has not been established. A retrospective evaluation was conducted on longitudinal clinical records of 811 myeloma patients treated at a tertiary centre (2001-2026), covering 44,962 documents and 1,334,677 laboratory values, with external validation on MIMIC-IV. An agentic reasoning system was compared against single-pass retrieval-augmented generation (RAG), iterative RAG, and full-context input on 469 patient-question pairs from 48 templates at three complexity levels. Reference labels came from double annotation by four oncologists with senior haematologist adjudication. Iterative RAG and full-context input converged on a shared ceiling (75.4% vs 75.8%, p = 1.00). The agentic system reached 79.6% concordance (95% CI 76.4-82.8), exceeding both baselines (+3.8 and +4.2 pp; p = 0.006 and 0.007). Gains rose with question complexity, reaching +9.4 pp on criteria-based synthesis (p = 0.032), and with record length, reaching +13.5 pp in the top decile (n = 10). The system error rate (12.2%) was comparable to expert disagreement (13.6%), but severity was inverted: 57.8% of system errors were clinically significant versus 18.8% of expert disagreements. Agentic reasoning was the only approach to exceed the shared ceiling, with gains concentrated on the most complex questions and longest records. The greater clinical consequence of residual system errors indicates that prospective evaluation in routine care is required before these findings translate into patient benefit.

cs.AI↗

arXiv2025

PARROT: An Open Multilingual Radiology Reports Dataset

Rationale and Objectives: To develop and validate PARROT (Polyglottal Annotated Radiology Reports for Open Testing), a large, multicentric, open-access dataset of fictional radiology reports spanning multiple languages for testing natural language processing applications in radiology. Materials and Methods: From May to September 2024, radiologists were invited to contribute fictional radiology reports following their standard reporting practices. Contributors provided at least 20 reports with associated metadata including anatomical region, imaging modality, clinical context, and for non-English reports, English translations. All reports were assigned ICD-10 codes. A human vs. AI report differentiation study was conducted with 154 participants (radiologists, healthcare professionals, and non-healthcare professionals) assessing whether reports were human-authored or AI-generated. Results: The dataset comprises 2,658 radiology reports from 76 authors across 21 countries and 13 languages. Reports cover multiple imaging modalities (CT: 36.1%, MRI: 22.8%, radiography: 19.0%, ultrasound: 16.8%) and anatomical regions, with chest (19.9%), abdomen (18.6%), head (17.3%), and pelvis (14.1%) being most prevalent. In the differentiation study, participants achieved 53.9% accuracy (95% CI: 50.7%-57.1%) in distinguishing between human and AI-generated reports, with radiologists performing significantly better (56.9%, 95% CI: 53.3%-60.6%, p<0.05) than other groups. Conclusion: PARROT represents the largest open multilingual radiology report dataset, enabling development and validation of natural language processing applications across linguistic, geographic, and clinical boundaries without privacy constraints.

cs.CL↗

arXiv2024

MRSegmentator: Multi-Modality Segmentation of 40 Classes in MRI and CT

Purpose: To develop and evaluate a deep learning model for multi-organ segmentation of MRI scans. Materials and Methods: The model was trained on 1,200 manually annotated 3D axial MRI scans from the UK Biobank, 221 in-house MRI scans, and 1228 CT scans from the TotalSegmentator dataset. A human-in-the-loop annotation workflow was employed, leveraging cross-modality transfer learning from an existing CT segmentation model to segment 40 anatomical structures. The annotation process began with a model based on transfer learning between CT and MR, which was iteratively refined based on manual corrections to predicted segmentations. The model's performance was evaluated on MRI examinations obtained from the German National Cohort (NAKO) study (n=900) from the AMOS22 dataset (n=60) and from the TotalSegmentator-MRI test data (n=29). The Dice Similarity Coefficient (DSC) and Hausdorff Distance (HD) were used to assess segmentation quality, stratified by organ and scan type. The model and its weights will be open-sourced. Results: MRSegmentator demonstrated high accuracy for well-defined organs (lungs: DSC 0.96, heart: DSC 0.94) and organs with anatomic variability (liver: DSC 0.96, kidneys: DSC 0.95). Smaller structures showed lower accuracy (portal/splenic veins: DSC 0.64, adrenal glands: DSC 0.69). On external validation using NAKO data, mean DSC ranged from 0.85 $\pm$ 0.08 for T2-HASTE to 0.91 $\pm$ 0.05 for in-phase sequences. The model generalized well to CT, achieving mean DSC of 0.84 $\pm$ 0.11 on AMOS CT data. Conclusion: MRSegmentator accurately segments 40 anatomical structures in MRI across diverse datasets and imaging protocols, with additional generalizability to CT images. This open-source model will provide a valuable tool for automated multi-organ segmentation in medical imaging research. It can be downloaded from https://github.com/hhaentze/MRSegmentator.

eess.IV↗

arXiv2023

Evaluation of GPT-4 for chest X-ray impression generation: A reader study on performance and perception

The remarkable generative capabilities of multimodal foundation models are currently being explored for a variety of applications. Generating radiological impressions is a challenging task that could significantly reduce the workload of radiologists. In our study we explored and analyzed the generative abilities of GPT-4 for Chest X-ray impression generation. To generate and evaluate impressions of chest X-rays based on different input modalities (image, text, text and image), a blinded radiological report was written for 25-cases of the publicly available NIH-dataset. GPT-4 was given image, finding section or both sequentially to generate an input dependent impression. In a blind randomized reading, 4-radiologists rated the impressions and were asked to classify the impression origin (Human, AI), providing justification for their decision. Lastly text model evaluation metrics and their correlation with the radiological score (summation of the 4 dimensions) was assessed. According to the radiological score, the human-written impression was rated highest, although not significantly different to text-based impressions. The automated evaluation metrics showed moderate to substantial correlations to the radiological score for the image impressions, however individual scores were highly divergent among inputs, indicating insufficient representation of radiological quality. Detection of AI-generated impressions varied by input and was 61% for text-based impressions. Impressions classified as AI-generated had significantly worse radiological scores even when written by a radiologist, indicating potential bias. Our study revealed significant discrepancies between a radiological assessment and common automatic evaluation metrics depending on the model input. The detection of AI-generated findings is subject to bias that highly rated impressions are perceived as human-written.

cs.CL↗

arXiv2021

Efficient, high-performance pancreatic segmentation using multi-scale feature extraction

For artificial intelligence-based image analysis methods to reach clinical applicability, the development of high-performance algorithms is crucial. For example, existent segmentation algorithms based on natural images are neither efficient in their parameter use nor optimized for medical imaging. Here we present MoNet, a highly optimized neural-network-based pancreatic segmentation algorithm focused on achieving high performance by efficient multi-scale image feature utilization.

eess.IV↗